Principal Software Engineer (AI)
Role details
Job location
Tech stack
Job description
The Principal Software Engineer (AI) will provide technical leadership in the design and delivery of production-grade, GenAI-enabled capabilities across IDBS platforms. The role focuses on applying large language models to real enterprise data: scientific, clinical, and operational to enable AI-driven discoverability, summarisation, reporting, and decision support.
Operating at principal level, you will be hands on, guiding teams through the transition from POC to early adoption and general release and help establish sustainable AI engineering practices across the department.
The engineer will collaborate closely with data scientists, bioinformaticians, and domain experts to deliver intelligent solutions for knowledge extraction, decision support, and workflow automation.
In this role, you will have the opportunity to:
- Lead the delivery of AI-enabled platform capabilities that accelerate insight and decision making across drug discovery, clinical development, and commercial operations.
- Design and productionise scalable GenAI solutions using approaches such as retrieval augmented generation (RAG), MCP-style integrations, and selectively applied agentic patterns, balancing capability, cost, performance, and trust to deliver measurable value from proof-of-concept through early adoption and general release.
- Translate scientific and business use cases into robust AI system designs that integrate cleanly with data platforms, workflows, and APIs.
- Establish engineering best practices for GenAI/LLM applications, including system design patterns, evaluation approaches, reliability, scalability, and maintainability standards across the AI engineering lifecycle.
- Act as a technical leader by mentoring engineers, influencing architectural direction, and driving the successful delivery and adoption of GenAI capabilities across IDBS platforms.
The essential requirements of the job include:
- Designing, building, and operating LLM-powered capabilities such as document summarisation, retrieval augmented generation (RAG), and question answering over enterprise datasets.
- Developing AI-ready data foundations, including unstructured data pipelines, metadata extraction and enrichment, and hybrid architectures using vector stores alongside relational databases.
- Proven ability to deploy AI systems into production environments, with effective monitoring of model behaviour, data drift, cost, and latency, and the judgment to make pragmatic trade-offs for reliability, scalability, and enterprise adoption.
- Establishing robust operational practices, including versioning of prompts, models, and data, and implementing feature flags and controlled rollout strategies for AI capabilities.
- Collaborating effectively with cross-functional partners (e.g., data science and domain experts), provide technical leadership, and mentor others while driving delivery in complex environments.
Requirements
- Experience applying GenAI solutions in life sciences / biopharma contexts, including scientific, clinical, or regulated (GxP-aligned) environments.
- Familiarity with building AI capabilities that support knowledge extraction, decision support, and workflow automation across enterprise data ecosystems, including cloud-based platforms such as Databricks and AWS.
- Experience defining or contributing to organisational best practices for AI engineering, including evaluation methods, governance, and scalable adoption approaches for generative/agentic AI.